diff options
author | Cheng Lian <lian@databricks.com> | 2015-02-17 23:36:20 -0800 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2015-02-17 23:36:20 -0800 |
commit | 61ab08549cb6fceb6de1b5c490c55a89d4bd28fa (patch) | |
tree | 172480f72bb84b685b39acd1e744c84a5dc42d40 /examples | |
parent | 3912d332464dcd124c60b734724c34d9742466a4 (diff) | |
download | spark-61ab08549cb6fceb6de1b5c490c55a89d4bd28fa.tar.gz spark-61ab08549cb6fceb6de1b5c490c55a89d4bd28fa.tar.bz2 spark-61ab08549cb6fceb6de1b5c490c55a89d4bd28fa.zip |
[Minor] [SQL] Cleans up DataFrame variable names and toDF() calls
Although we've migrated to the DataFrame API, lots of code still uses `rdd` or `srdd` as local variable names. This PR tries to address these naming inconsistencies and some other minor DataFrame related style issues.
<!-- Reviewable:start -->
[<img src="https://reviewable.io/review_button.png" height=40 alt="Review on Reviewable"/>](https://reviewable.io/reviews/apache/spark/4670)
<!-- Reviewable:end -->
Author: Cheng Lian <lian@databricks.com>
Closes #4670 from liancheng/df-cleanup and squashes the following commits:
3e14448 [Cheng Lian] Cleans up DataFrame variable names and toDF() calls
Diffstat (limited to 'examples')
8 files changed, 14 insertions, 14 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/CrossValidatorExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/CrossValidatorExample.scala index f0241943ef..7ab892cd75 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/CrossValidatorExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/CrossValidatorExample.scala @@ -90,7 +90,7 @@ object CrossValidatorExample { crossval.setNumFolds(2) // Use 3+ in practice // Run cross-validation, and choose the best set of parameters. - val cvModel = crossval.fit(training.toDF) + val cvModel = crossval.fit(training.toDF()) // Prepare test documents, which are unlabeled. val test = sc.parallelize(Seq( diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/DeveloperApiExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/DeveloperApiExample.scala index 54aadd2288..df26798e41 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/DeveloperApiExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/DeveloperApiExample.scala @@ -58,7 +58,7 @@ object DeveloperApiExample { lr.setMaxIter(10) // Learn a LogisticRegression model. This uses the parameters stored in lr. - val model = lr.fit(training.toDF) + val model = lr.fit(training.toDF()) // Prepare test data. val test = sc.parallelize(Seq( @@ -67,7 +67,7 @@ object DeveloperApiExample { LabeledPoint(1.0, Vectors.dense(0.0, 2.2, -1.5)))) // Make predictions on test data. - val sumPredictions: Double = model.transform(test.toDF) + val sumPredictions: Double = model.transform(test.toDF()) .select("features", "label", "prediction") .collect() .map { case Row(features: Vector, label: Double, prediction: Double) => diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/MovieLensALS.scala b/examples/src/main/scala/org/apache/spark/examples/ml/MovieLensALS.scala index adaf796dc1..96b2dd463e 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/MovieLensALS.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/MovieLensALS.scala @@ -137,9 +137,9 @@ object MovieLensALS { .setRegParam(params.regParam) .setNumBlocks(params.numBlocks) - val model = als.fit(training.toDF) + val model = als.fit(training.toDF()) - val predictions = model.transform(test.toDF).cache() + val predictions = model.transform(test.toDF()).cache() // Evaluate the model. // TODO: Create an evaluator to compute RMSE. @@ -158,7 +158,7 @@ object MovieLensALS { // Inspect false positives. predictions.registerTempTable("prediction") - sc.textFile(params.movies).map(Movie.parseMovie).toDF.registerTempTable("movie") + sc.textFile(params.movies).map(Movie.parseMovie).toDF().registerTempTable("movie") sqlContext.sql( """ |SELECT userId, prediction.movieId, title, rating, prediction diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala index c5bb5515b1..e8af5c1625 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala @@ -58,7 +58,7 @@ object SimpleParamsExample { .setRegParam(0.01) // Learn a LogisticRegression model. This uses the parameters stored in lr. - val model1 = lr.fit(training.toDF) + val model1 = lr.fit(training.toDF()) // Since model1 is a Model (i.e., a Transformer produced by an Estimator), // we can view the parameters it used during fit(). // This prints the parameter (name: value) pairs, where names are unique IDs for this @@ -77,7 +77,7 @@ object SimpleParamsExample { // Now learn a new model using the paramMapCombined parameters. // paramMapCombined overrides all parameters set earlier via lr.set* methods. - val model2 = lr.fit(training.toDF, paramMapCombined) + val model2 = lr.fit(training.toDF(), paramMapCombined) println("Model 2 was fit using parameters: " + model2.fittingParamMap) // Prepare test data. @@ -90,7 +90,7 @@ object SimpleParamsExample { // LogisticRegression.transform will only use the 'features' column. // Note that model2.transform() outputs a 'myProbability' column instead of the usual // 'probability' column since we renamed the lr.probabilityCol parameter previously. - model2.transform(test.toDF) + model2.transform(test.toDF()) .select("features", "label", "myProbability", "prediction") .collect() .foreach { case Row(features: Vector, label: Double, prob: Vector, prediction: Double) => diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala b/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala index 8b47f88e48..a11db6fd5c 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala @@ -69,7 +69,7 @@ object SimpleTextClassificationPipeline { .setStages(Array(tokenizer, hashingTF, lr)) // Fit the pipeline to training documents. - val model = pipeline.fit(training.toDF) + val model = pipeline.fit(training.toDF()) // Prepare test documents, which are unlabeled. val test = sc.parallelize(Seq( @@ -79,7 +79,7 @@ object SimpleTextClassificationPipeline { Document(7L, "apache hadoop"))) // Make predictions on test documents. - model.transform(test.toDF) + model.transform(test.toDF()) .select("id", "text", "probability", "prediction") .collect() .foreach { case Row(id: Long, text: String, prob: Vector, prediction: Double) => diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/DatasetExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/DatasetExample.scala index c98c68a02f..e943d6c889 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/DatasetExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/DatasetExample.scala @@ -81,7 +81,7 @@ object DatasetExample { println(s"Loaded ${origData.count()} instances from file: ${params.input}") // Convert input data to DataFrame explicitly. - val df: DataFrame = origData.toDF + val df: DataFrame = origData.toDF() println(s"Inferred schema:\n${df.schema.prettyJson}") println(s"Converted to DataFrame with ${df.count()} records") diff --git a/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala b/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala index 79d3d5a24c..6331d1c006 100644 --- a/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala +++ b/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala @@ -34,7 +34,7 @@ object RDDRelation { // Importing the SQL context gives access to all the SQL functions and implicit conversions. import sqlContext.implicits._ - val df = sc.parallelize((1 to 100).map(i => Record(i, s"val_$i"))).toDF + val df = sc.parallelize((1 to 100).map(i => Record(i, s"val_$i"))).toDF() // Any RDD containing case classes can be registered as a table. The schema of the table is // automatically inferred using scala reflection. df.registerTempTable("records") diff --git a/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala b/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala index 7128deba54..b7ba60ec28 100644 --- a/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala +++ b/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala @@ -68,7 +68,7 @@ object HiveFromSpark { // You can also register RDDs as temporary tables within a HiveContext. val rdd = sc.parallelize((1 to 100).map(i => Record(i, s"val_$i"))) - rdd.toDF.registerTempTable("records") + rdd.toDF().registerTempTable("records") // Queries can then join RDD data with data stored in Hive. println("Result of SELECT *:") |